Learning Data Mining with Python - Second Edition

Distance metrics

A key underlying concept in data mining is that of distance. If we have two samples, we need to answer questions such as are these two samples more similar than the other two? Answering questions like these is important to the outcome of the data mining exercise.

The most common use is Euclidean distance, which is the real-world distance between two objects. If you were to plot the points on a graph and measure the distance with a ruler, the result would be the Euclidean distance. 

A little more formally, the Euclidean distances between points a and b is the square root of the sum of the squared distances for each feature.

Euclidean distance is intuitive but provides poor accuracy if some features have larger values than ...